Can Computers Outperform Humans in Detecting User Zone-Outs? Implications for Intelligent Interfaces

The ability to identify whether a user is “zoning out” (mind wandering) from video has many HCI (e.g., distance learning, high-stakes vigilance tasks). However, it remains unknown how well humans can perform this task, how they compare to automatic computerized approaches, and how a fusion of the two might improve accuracy. We analyzed videos of users’ faces and upper bodies recorded 10s prior to self-reported mind wandering (i.e., ground truth) while they engaged in a computerized reading task. We found that a state-of-the-art machine learning model had comparable accuracy to aggregated judgments of nine untrained human observers (area under receiver operating characteristic curve [AUC] = .598 versus .589). A fusion of the two (AUC = .644) outperformed each, presumably because each focused on complementary cues. Furthermore, adding more humans beyond 3–4 observers yielded diminishing returns. We discuss implications of human–computer fusion as a means to improve accuracy in complex tasks.

Enhancing Intelligent Anemia Detection via Unifying Global and Local Views of Conjunctiva Image with Two-Branch Neural Networks

Anemia is one of the most widespread clinical symptoms all over the world, which could bring adverse effects on people's daily life and work. Considering the universality of anemia detection and the inconvenience of traditional blood testing methods, many deep learning detection methods based on image recognition have been developed in recent years, including the methods of anemia detection with individuals’ images of conjunctiva. However, existing methods using one single conjunctiva image could not reach comparable accuracy in anemia detection in many real-world application scenarios. To enhance intelligent anemia detection using conjunctiva images, we proposed a new algorithmic framework which could make full use of the data information contained in the image. To be concrete, we proposed to fully explore the global and local information in the image, and adopted a two-branch neural network architecture to unify the information of these two aspects. Compared with the existing methods, our method can fully explore the information contained in a single conjunctiva image and achieve more reliable anemia detection effect. Compared with other existing methods, the experimental results verified the effectiveness of the new algorithm.

A Lightweight Keypoint Matching Framework for Morphometric Landmark Detection

Geometric morphometrics has become an important approach in insect morphology studies because it capitalizes on advanced quantitative methods to analyze shape. Shape could be digitized as a set of landmarks from specimen images. However, the existing tools mostly require manual landmark digitization, and previous works on automatic landmark detection methods do not focus on implementation for end-users. Motivated by that, we propose a novel approach for automatic landmark detection, based on visual features of landmarks and keypoint matching techniques. While still archiving comparable accuracy to that of the state-of-the-art method, our framework requires less initial annotated data to build prediction model and runs faster. It is lightweight also in terms of implementation, in which a four-step workflow is provided with user-friendly graphical interfaces to produce correct landmark coordinates both by model prediction and manual correction. The utility iMorph is freely available at https://github.com/ha-usth/WingLanmarkPredictor, currently supporting Windows, MacOS, and Linux.

Efficient iterative Hi-C scaffolder based on N-best neighbors

Background Efficient and effective genome scaffolding tools are still in high demand for generating reference-quality assemblies. While long read data itself is unlikely to create a chromosome-scale assembly for most eukaryotic species, the inexpensive Hi-C sequencing technology, capable of capturing the chromosomal profile of a genome, is now widely used to complete the task. However, the existing Hi-C based scaffolding tools either require a priori chromosome number as input, or lack the ability to build highly continuous scaffolds. Results We design and develop a novel Hi-C based scaffolding tool, pin_hic, which takes advantage of contact information from Hi-C reads to construct a scaffolding graph iteratively based on N-best neighbors of contigs. Subsequent to scaffolding, it identifies potential misjoins and breaks them to keep the scaffolding accuracy. Through our tests on three long read based de novo assemblies from three different species, we demonstrate that pin_hic is more efficient than current standard state-of-art tools, and it can generate much more continuous scaffolds, while achieving a higher or comparable accuracy. Conclusions Pin_hic is an efficient Hi-C based scaffolding tool, which can be useful for building chromosome-scale assemblies. As many sequencing projects have been launched in the recent years, we believe pin_hic has potential to be applied in these projects and makes a meaningful contribution.

A deep-learning model for predictive archaeology and archaeological community detection

Deep learning is a powerful tool for exploring large datasets and discovering new patterns. This work presents an account of a metric learning-based deep convolutional neural network (CNN) applied to an archaeological dataset. The proposed account speaks of three stages: training, testing/validating, and community detection. Several thousand artefact images, ranging from the Lower Palaeolithic period (1.4 million years ago) to the Late Islamic period (fourteenth century AD), were used to train the model (i.e., the CNN), to discern artefacts by site and period. After training, it attained a comparable accuracy to archaeologists in various periods. In order to test the model, it was called to identify new query images according to similarities with known (training) images. Validation blinding experiments showed that while archaeologists performed as well as the model within their field of expertise, they fell behind concerning other periods. Lastly, a community detection algorithm based on the confusion matrix data was used to discern affiliations across sites. A case-study on Levantine Natufian artefacts demonstrated the algorithm’s capacity to discern meaningful connections. As such, the model has the potential to reveal yet unknown patterns in archaeological data.

Pregnancy Labor Prediction Using Magnetomyography Sensing and a Self-Sorting Cybernetic Model

To date, effective means of predicting pregnancy labor continues to lack. Magnetic field signals during uterine contraction have shown, in recent studies, to be a good source of information for predicting labor state with a greater accuracy compared with existing methods. The means of labor prediction methods from such signals appear to rely on a supervised learning post-processing framework whose calibration relies on an effective labelling of the training sample set. As a potential solution to this, using a reduced electrode channel from magnetomyography instrumentation, we propose a multi-stage self-sorting cybernetic model that is comprised of an ensemble of various post-processing methods, and is underpinned by an unsupervised learning framework that allows for an automated method towards learning from the trend in the data to infer labor state and imminency. Experimental results showed a comparable accuracy with those from a supervised learning method adopted in a prior study. Additionally, an architecture of how an intelligent cybernetic model can be used for labor prediction and cost saving benefits within a clinical setting is offered by this study.

Intermittent-Aware Neural Architecture Search

The increasing paradigm shift towards i ntermittent computing has made it possible to intermittently execute d eep neural network (DNN) inference on edge devices powered by ambient energy. Recently, n eural architecture search (NAS) techniques have achieved great success in automatically finding DNNs with high accuracy and low inference latency on the deployed hardware. We make a key observation, where NAS attempts to improve inference latency by primarily maximizing data reuse, but the derived solutions when deployed on intermittently-powered systems may be inefficient, such that the inference may not satisfy an end-to-end latency requirement and, more seriously, they may be unsafe given an insufficient energy budget. This work proposes iNAS, which introduces intermittent execution behavior into NAS to find accurate network architectures with corresponding execution designs, which can safely and efficiently execute under intermittent power. An intermittent-aware execution design explorer is presented, which finds the right balance between data reuse and the costs related to intermittent inference, and incorporates a preservation design search space into NAS, while ensuring the power-cycle energy budget is not exceeded. To assess an intermittent execution design, an intermittent-aware abstract performance model is presented, which formulates the key costs related to progress preservation and recovery during intermittent inference. We implement iNAS on top of an existing NAS framework and evaluate their respective solutions found for various datasets, energy budgets and latency requirements, on a Texas Instruments device. Compared to those NAS solutions that can safely complete the inference, the iNAS solutions reduce the intermittent inference latency by 60% on average while achieving comparable accuracy, with an average 7% increase in search overhead.

Magnetorheological damper modeling based on a refined constitutive model for MR fluids

A systematic modeling study is conducted to predict the dynamic response of magnetorheological (MR) damper based on a refined constitutive model for MR fluids. A particle-level simulation method is first employed to probe the microstructured behavior and rheological properties of MR fluids, based on which the refined constitutive model is developed. The constitutive model is further validated by comparing the predicted results with the data obtained from microscopic simulations and existing experiments. It is revealed that the proposed constitutive model has comparable accuracy and good applicability in representing MR fluids. Subsequently, a computational fluid dynamics (CFD) model is established to explore MR damper’s behavior by using the proposed constitutive model to describe the fluid rheology. For better capturing the dynamic hysteretic behavior of MR damper, a modified parametric model is developed by combing the Bingham plastic model and the proposed constitutive model. The modified model for MR damper shows its validity and superiority over the existing Bingham plastic models.

An Update of the Benton Facial Recognition Test

The Benton Facial Recognition Test (BFRT) is a paper-and-pen task that is traditionally used to assess face perception skills in neurological, clinical and psychiatric conditions. Despite criticisms of its stimuli, the task enjoys a simple procedure and is rapid to administer. Further, it has recently been computerised (BFRT-c), allowing reliable measurement of completion times and the need for online testing. Here, in response to calls for repeat-screening for the accurate detection of face processing deficits, we present the BFRT-Revised (BFRT-r): a new version of the BFRT-c that maintains the task’s basic paradigm, but employs new, higher quality stimuli that reflect recent theoretical advances in the field. An initial validation study with typical participants indicated that the BFRT-r has good internal reliability and content validity. A second investigation indicated that while younger and older participants had comparable accuracy, completion times were longer in the latter, highlighting the need for age-matched norms. Administration of the BFRT-r and BFRT-c to 32 individuals with developmental prosopagnosia resulted in improved sensitivity in diagnostic screening for the BFRT-r compared to the BFRT-c. These findings are discussed in relation to current diagnostic screening protocols for face perception deficits. The BFRT-r is stored in an open repository and is freely available to other researchers.

Estimation of Wiebe Function Parameters for Syngas and Anode Off-Gas Combustion in Spark-Ignition Engines

Wiebe functions, analytical equations that estimate the fuel mass fraction burned (MFB) during combustion, have been effective at describing spark-ignition (SI) engine combustion using gasoline fuels. This study explores if the same methodology can be extended for SI combustion with syngas, a gaseous fuel mixture composed of H2, CO, and CO2, and anode-off gas; the latter is an exhaust gas mixture emitted from the anode of a Solid Oxide Fuel Cell, containing H2, CO, H2O, and CO2. For this study, anode off-gas is treated as a syngas fuel diluted with CO2 and vaporized water. Combustion experiments were run on a single-cylinder, research engine using syngas and anode-off gas as fuels. One single Wiebe function and three double Wiebe functions were fitted and compared with the MFB profile calculated from the experimental data. It was determined that the SI combustion process of both the syngas and the anode-off gas could be estimated using a governing Wiebe function. While the detailed double Wiebe function had the highest accuracy, a reduced double Wiebe function is capable of achieving comparable accuracy. On the other hand, a single Wiebe function is not able to fully capture the combustion process of a SI engine using syngas and anode off-gas.